Logo des Repositoriums

Auflistung nach Autor:in "Seipolt, Arne"

1 - 3 von 3
  • Konferenzbeitrag
    Assessing the performance of Neural Networks in Recognizing Manual Labor Actions in a Production Environment
    (INFORMATIK 2023 - Designing Futures: Zukünfte gestalten, 2023) Höfinghoff, Maximilian; Buschermöhle, Ralf; Korn, Goy-Hinrich; Schumacher, Marcel; Seipolt, Arne
    Action recognition technology has gained significant traction in recent years. This paper focuses on evaluating neural network architectures for action recognition in the production industry. By utilizing datasets tailored for production or assembly tasks, various architectures are assessed for their accuracy and performance. The findings of this study provide some insights and guidance for researchers and practitioners to select an appropriate architecture or pretrained models for action recognition in the production industry.
  • Konferenzbeitrag
    Enhancing Digital Twins for Production through Process Mining Techniques: A Literature Review
    (INFORMATIK 2023 - Designing Futures: Zukünfte gestalten, 2023) Schumacher, Marcel; Buschermöhle, Ralf; Haak, Liane; Höfinghoff, Max; Seipolt, Arne; Korn, Goy-Hinrich
    A digital twin (DT) plays a vital role in the advancement of manufacturers towards Industry 4.0. However, the creation and maintenance of DTs can be time-consuming. One approach to streamline this process is the utilization of process mining (PM) methods and techniques, which can automatically generate valuable information for DTs. Therefore, this paper aims to examine different approaches that augment DTs with PM and explore their effects. The review categorizes these approaches into three groups: theoretical approaches, approaches with laboratory case studies, and approaches with real-world case studies conducted by manufacturers. The review reveals that the use of PM can enhance the flexibility and sustainability of DTs. However, this improvement comes at the cost of requiring high-quality data and more data preparation efforts.
  • Konferenzbeitrag
    Technology Readiness Levels of Reinforcement Learning methods for simulation-based production scheduling
    (INFORMATIK 2023 - Designing Futures: Zukünfte gestalten, 2023) Seipolt, Arne; Buschermöhle, Ralf; Höfinghoff, Maximilian; Korn, Goy-Hinrich; Schumacher, Marcel
    Digital Twins (DT) are nowadays widely used and provide a benefit for the companies using it. One service of the DT is the simulation of a production process. This enables an optimization of the production process by simulation optimization, for example with Reinforcement Learning (RL). To support researchers and practitioners in deciding which algorithm is suitable for an implementation under real-life conditions, a literature research is performed, and a Machine Learning Technology Readiness Level is assigned to the different RL-Algorithms. It can be shown that recent research focuses mainly on model free value based and evolutionary algorithms, and both are suitable for an implementation in a real-world scenario. Both algorithms can outperform widely applied dispatching rules. Nevertheless, it should be evaluated why other algorithms are not in the focus of recent research and how the algorithms perform in comparison to each other.